Apple M3 Ultra GPU (80-core) vs Pro GPU (18-core)
VS
Apple M3 Ultra GPU (80-core)
Custom
Apple M3 Pro GPU (18-core)
Custom
We performed a head-to-head comparison of the Apple M3 Ultra GPU (80-core) with 1280 pipelines and 10240 shaders against the 1 year and 4 months older Pro GPU (18-core) that utilizes 288 pipelines and 2304 shaders. Here you will find complete details about specs, efficiency, performance tests, and more.
Review
Gaming
Performance in DirectX, OpenCL, and Vulkan games
Workstation
Perf. in 3D modeling, video editing and rendering apps
AI/ML
Capabilities for machine learning and AI-related tasks
Energy Efficiency
Power consumption efficiency in different scenarios
NanoReview Final Score
Overall video card score
The "Energy Efficiency" metric has less impact on the NanoReview Score for desktop GPU.
Key differences
Reasons to consider the Apple M3 Ultra GPU (80-core)
- Performs significantly better (up to 3.2x) in 3DMark Steel Nomad Lite
- 4.4x higher maximum theoretical performance (28.3 vs 6.4 TFLOPS)
- Has 5.3x higher memory bandwidth: 819.3 vs 153.6 GB/s
- Achieves 3.4x more points in the GeekBench 6 Compute test (147K vs 43K)
- Has 4.4x more shading units (10240 vs 2304)
Benchmarks
Graphics cards’ performance in recent benchmarking apps3D Mark
Steel Nomad Lite Score
| Solar Bay | 63597 | 22637 |
| Wild Life Extreme | 47814 | 14021 |
GeekBench 6 OpenCL
GB6 Compute Score
| Background Blur | 204.5 img/sec | 82.1 img/sec |
| Face Detection | 126 img/sec | 53.6 img/sec |
| Horizon Detection | 6.53 Gpixels/sec | 1.82 Gpixels/sec |
| Edge Detection | 10.7 Gpixels/sec | 2.59 Gpixels/sec |
| Gaussian Blur | 9.5 Gpixels/sec | 1.84 Gpixels/sec |
| Feature Matching | 1.05 Gpixels/sec | 0.48 Gpixels/sec |
| Stereo Matching | 560.3 Gpixels/sec | 148.6 Gpixels/sec |
| Particle Physics | 25267.8 FPS | 4893.9 FPS |
| API | OpenCL | OpenCL |
Cinebench 2024 GPU
Cinebench 2024 GPU
Blender
Blender GPU
Recent User Tests
Apple M3 Ultra GPU (80-core)
| Date | Benchmark | Result |
|---|---|---|
| 📘 2025-03-16 (Tyler) | Geekbench 6 OpenCL | 145706 |
| 📘 2025-03-16 (Tyler) | Cinebench 2024 | 19448 |
Apple M3 Pro GPU (18-core)
No benchmark results yet
Artificial Intelligence Tests
Performance in machine learning and artificial intelligence tasksGeekBench 6 ML
GB6 ML Single Precision
GB6 ML Half Precision
GB6 ML Quantized
| Image Classification (SP) | 8094 | 5578 |
| Image Segmentation (HP) | 24595 | 9924 |
| Image Super Resolution (Q) | 25190 | 13323 |
| Face Detection (HP) | 38337 | 19900 |
| Pose Estimation (Q) | 111021 | 35730 |
| Text Classification (SP) | 2786 | 2904 |
| Machine Translation (HP) | 4339 | 4985 |
| Object Detection (SP) | 7668 | 5496 |
| Depth Estimation (Q) | 37488 | 23344 |
| Style Transfer (SP) | 244483 | 78342 |
| Framework | Core ML | Core ML |
| Backend | GPU | GPU |
Specifications
Technical specifications of Apple M3 Ultra GPU (80-core) and Pro GPU (18-core)General
| Vendor | Apple | Apple |
| Build | Integrated | Integrated |
| Released | March 5, 2025 | October 31, 2023 |
| Case | Desktop | Laptop |
| Purpose | Professional | Professional |
| Segment | High-end | Mid-range |
| Architecture | Apple M GPU | Apple M GPU |
| GPU Codename | Custom | Custom |
| Rival Equivalent | - GeForce RTX 5070 Ti | - GeForce RTX 4060 Laptop |
| Successor | - Apple M4 Ultra GPU (80-core) | - Apple M5 Pro GPU (20-core) |
| Recommended CPU | - Apple M3 Ultra or above | - Apple M3 Pro or above |
| Used in CPUs | - Apple M3 Ultra | - Apple M3 Pro |
Desktop GPU rating (#29th place)
Laptop GPU ranking (#61st place)
Graphics Processing Unit
| Base Clock | - | 500 MHz |
| Boost Clock | 1380 MHz | 1380 MHz |
| Shading Units | 10240 | 2304 |
| Texture Mapping Units (TMUs) | 640 | 144 |
| Render Output Units (ROPs) | 320 | 72 |
| Compute Units (Pipelines) | 1280 | 288 |
| Instructions Per Cycle | 2 IPC | 2 IPC |
Raw Performance
| Pixel Fill Rate | 442 GPixel/s | 99 GPixel/s |
| Texture Fill Rate | 883 GTexel/s | 199 GTexel/s |
FLOPS (FP32)
Physical
| Interface | Custom | Custom |
| TGP | 140 W | 30 W |
| Manufacturing | TSMC | TSMC |
| Fabrication Process | 3 nm | 3 nm |
| Transistor Count | 184 billion | 25.2 billion |
| Max. Temperature | 100°C | 100°C |
Memory
| Memory Type | System Shared | System Shared |
| Memory Clock | 6400 MHz | 6400 MHz |
| Effective Memory Speed | - | 12800 Mbps |
| Bus | 1024-bit | 192-bit |
| ECC | No | No |
Memory Bandwidth
API
| Ray Tracing | Yes | Yes |
| DLSS | No | No |
Cast your vote
Total votes: 1